Search papers, labs, and topics across Lattice.
3
0
9
0
LLMs can learn to self-correct social biases during chain-of-thought reasoning by strategically reallocating probability mass, outperforming existing debiasing methods with minimal supervision.
Forget full fine-tuning: SpecMamba unlocks parameter-efficient few-shot hyperspectral target detection by decoupling semantic representation from agile spectral adaptation using a frequency-aware Mamba adapter.
By injecting symbolic reasoning into vision-language-action models, NS-VLA achieves remarkable gains in data efficiency and generalization for robotic manipulation.
